This research introduces an original approach to time series forecasting through the use of multi-scale convolutional neural networks with Transformer modules. The objective is to focus on the limitations of short-term load forecasting in terms of complex spatio-temporal dependencies. The model begins with the convolutional layers, which perform feature extraction from the time series data to look for features with different temporal resolutions. The last step involves making use of the self-attention component of the Transformer block, which tries to find the long-range dependencies within the series. Also, a spatial attention layer is included to handle the interactions among the different samples. Equipped with these features, the model is able to make predictions. Experimental results show that this model performs better compared to the time series forecasting models in the literature. It is worth mentioning that the MSE score or mean square error of the model was 0.62, while the measure of fit R² was 0.91 in predicting the individual household electric power consumption dataset. The baseline models for this dataset such as the LSTM model had an MSE of 2.324 and R² value of 0.79, showing that the proposed model was significantly improved by a margin.

Objective. High-resolution functional magnetic resonance imaging (fMRI) is essential for mapping human brain activity; however, it remains costly and logistically challenging. If comparable volumes could be generated directly from widely available scalp electroencephalography (EEG), advanced neuroimaging would become significantly more accessible. Existing EEG-to-fMRI generators rely on plain convolutional neural networks that fail to capture cross-channel time–frequency cues or on heavy transformer/generative adversarial network decoders that strain memory and stability. Approach. To address these limitations, we propose Spec2VolCAMU-Net, a lightweight architecture featuring a Multi-directional Time–Frequency Convolutional Attention Encoder for rich feature extraction and a Vision-Mamba U-Net decoder that uses linear-time state-space blocks for efficient long-range spatial modeling. We frame the goal of this work as establishing a new state of the art in the spatial fidelity of single-volume reconstruction, a foundational prerequisite for the ultimate aim of generating temporally coherent fMRI time series. Main results. Trained end-to-end with a hybrid SSI-MSE loss, Spec2VolCAMU-Net achieves state-of-the-art fidelity on three public benchmarks, recording structural similarity index (SSIM) of 0.693 on NODDI, 0.725 on Oddball and 0.788 on CN-EPFL, representing improvements of 14.5%, 14.9%, and 16.9% respectively over previous best SSIM scores. Furthermore, it achieves competitive peak signal-to-noise ratio (PSNR) scores, particularly excelling on the CN-EPFL dataset with a 4.6% improvement over the previous best PSNR, thus striking a better balance in reconstruction quality. Significance. The proposed model is lightweight and efficient, making it suitable for real-time applications in clinical and research settings. The code is available at https://github.com/hdy6438/Spec2VolCAMU-Net .

Cardiovascular diseases require precise blood pressure monitoring, with central aortic pressure (CAP) being a stronger predictor of risk than peripheral arterial pressure (PAP). However, invasive methods for measuring CAP are accurate, they are costly and carry procedural risks, while non-invasive alternatives often lack accuracy and struggle to adapt to individual physiological differences. To address these limitations, this paper introduces R2A-MAGNet, a novel deep learning model that non-invasively reconstructs CAP waveforms from radial arterial pressure (RAP) waveforms. R2A-MAGNet combines CNNs for local feature extraction with GRUs, the Selective State Spaces Model (Mamba), Self-Attention, and Cross-Attention for global feature learning and enhanced information interaction. Tested on a real-world dataset, R2A-MAGNet outperforms existing models, achieving the lowest Mean Absolute Error for CAP (1.93 mmHg), RMSE for central systolic (2.77 mmHg), and RMSE for central diastolic pressure (1.48 mmHg). Visual and statistical analyses confirm its accuracy and reliability, underscoring its potential for advanced blood pressure monitoring.